© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9308
    Prev
    Next
    INDEX
    Explanations

    narrative elements and themes related to stories and personal transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "...part" or "taking part"

    np_acts-logits-general · gemini-2.0-flash

    part of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -1.02
    SharedCtor
    -0.70
    География
    -0.66
     viewDidLoad
    -0.65
     MainAxisSize
    -0.65
     kasarigan
    -0.63
    Попис
    -0.62
    enderror
    -0.61
    DeleteBehavior
    -0.60
    withIdentifier
    -0.59
    POSITIVE LOGITS
     part
    4.23
    part
    3.72
    Part
    3.39
     parts
    3.32
     parte
    3.18
     Part
    3.18
     PART
    2.93
    parts
    2.86
    PART
    2.63
     Teil
    2.56
    Activations Density 0.976%

    No Known Activations